mem0ai/mem0 · error · ValueError

AWS Bedrock error: {e}

Error message

AWS Bedrock error: {e}

What it means

Catch-all ValueError raised by _initialize_aws_client for any boto3 ClientError other than UnauthorizedOperation — e.g. AccessDeniedException on list_foundation_models (model access not enabled), ValidationException, ThrottlingException, or region misconfiguration. The underlying AWS error code and message are embedded via {e}, so inspect that text to classify the real cause.

Source

Thrown at mem0/llms/aws_bedrock.py:107

            self.client = boto3.client("bedrock-runtime", **aws_config)

            # Test connection
            self._test_connection()

        except NoCredentialsError:
            raise ValueError(
                "AWS credentials not found. Please set AWS_ACCESS_KEY_ID, "
                "AWS_SECRET_ACCESS_KEY, and AWS_REGION environment variables, "
                "or provide them in the config."
            )
        except ClientError as e:
            if e.response["Error"]["Code"] == "UnauthorizedOperation":
                raise ValueError(
                    f"Unauthorized access to Bedrock. Please ensure your AWS credentials "
                    f"have permission to access Bedrock in region {self.config.aws_region}."
                )
            else:
                raise ValueError(f"AWS Bedrock error: {e}")

    def _test_connection(self):
        """Test connection to AWS Bedrock service."""
        try:
            # List available models to test connection
            bedrock_client = boto3.client("bedrock", **self.config.get_aws_config())
            response = bedrock_client.list_foundation_models()
            self.available_models = [model["modelId"] for model in response["modelSummaries"]]

            # Check if our model is available
            if self.config.model not in self.available_models:
                logger.warning(f"Model {self.config.model} may not be available in region {self.config.aws_region}")
                logger.info(f"Available models: {', '.join(self.available_models[:5])}...")

        except Exception as e:
            logger.warning(f"Could not verify model availability: {e}")
            self.available_models = []

View on GitHub (pinned to 001c235229)

Solutions

1. Read the embedded error code in the message: AccessDeniedException -> enable model access in Bedrock console; ValidationException -> fix config; Throttling -> retry after backoff
2. Verify AWS_REGION is a Bedrock-supported region and matches the model's availability
3. Re-authenticate if ExpiredToken: refresh STS session or run aws sso login
4. Retry initialization with exponential backoff for throttling errors

Example fix

// before
# aws_region unset, defaults to unsupported region -> AWS Bedrock error

# after
Memory.from_config({"llm": {"provider": "aws_bedrock", "config": {
    "aws_region": "us-east-1", "model": "anthropic.claude-3-5-sonnet-20240620-v1:0"
}}})

import boto3
from botocore.exceptions import ClientError

try:
    boto3.client("bedrock", region_name=region).list_foundation_models()
except ClientError as e:
    code = e.response["Error"]["Code"]
    raise SystemExit(f"Bedrock preflight failed: {code}: {e}")  # classify before mem0 init

try:
    llm = AWSBedrockLLM(config)
except ValueError as e:
    msg = str(e)
    if "AccessDeniedException" in msg:
        fix = "enable model access in Bedrock console"
    elif "ThrottlingException" in msg:
        fix = "backoff and retry"
    else:
        fix = "inspect full AWS error text"
    raise RuntimeError(f"{msg} — suggested fix: {fix}") from e

When it happens

Trigger: Bedrock model access not enabled for the account (AccessDeniedException on ListFoundationModels); wrong AWS_REGION where Bedrock is unavailable; throttling during init; expired tokens surfacing as ExpiredTokenException

Common situations: New AWS account where Bedrock foundation models require console opt-in; unsupported region (e.g. some regions lack Bedrock); STS session tokens expired mid-run; rate limits hit at startup in multi-instance deployments.

Related errors

• The 'boto3' library is required. Please install it using 'pi
• Unknown provider_override '{explicit_provider}'. Valid provi
• Unknown provider in model: {model}
• AWS credentials not found. Please set AWS_ACCESS_KEY_ID, AWS
• Unauthorized access to Bedrock. Please ensure your AWS crede

AI-assisted analysis of mem0ai/mem0@001c235229 (2026-08-15). Data as JSON: /api/errors/27ed7a5ab4b688bb. Report an issue: GitHub.